arXiv:2610.16224v1 Announce Type: cross Abstract: Text-to-image models have made remarkable progress in visual fidelity and instruction following, yet complex compositional generation remains challen...
arXiv:2608.12743v3 Announce Type: replace Abstract: Spatial intelligence is becoming a foundation for embodied agents, robotic planning, and multimodal assistants. To improve the spatial reasoning ab...
arXiv:2608. 12743v1 Announce Type: new Abstract: Spatial intelligence is becoming a foundation for embodied agents, robotic planning, and multimodal assistants.
arXiv:2606. 27608v1 Announce Type: cross Abstract: We present Qwen-Image-2.
arXiv:2604. 16557v2 Announce Type: replace Abstract: Current post-training methodologies for adapting Large Vision-Language Models (LVLMs) generally fall into two paradigms: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL).
arXiv:2607. 17243v1 Announce Type: new Abstract: Multi-view spatial reasoning requires vision-language models to compare visual evidence across images, align object correspondences, and infer spatial relations over long visual contexts, a setting where chain-of-thought reasoning tends to grow verbose without becoming more accurate.
arXiv:2512. 03438v3 Announce Type: replace Abstract: Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers.
Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning. Recent reinforcement learning (RL) methods aim to close this gap with verifiable outcomes, yet they suffer from poor credit assignment across intermediate reasoning steps.
arXiv:2606. 11770v1 Announce Type: new Abstract: Spatial reasoning remains a challenge for Multimodal Large Language Models (MLLMs), as it requires reliable multi-hop inference over both intermediate states and state transitions.
The paper introduces Rollout-Time Intervention (RTI), a method that uses reward-side evidence during rollouts to transform unsuccessful trajectories into successful ones, thereby providing learning signals for tasks beyond a policy’s intrinsic exploration limits. RTI filters out trajectories with excessive distributional shifts, allowing these off-policy interventions to guide policy optimization effectively. Experiments on five benchmarks show that RTI consistently outperforms existing RL baselines, enabling post-trained policies to approach the performance of stronger large language models and surpass their original capability boundaries.
arXiv:2511. 07403v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial reasoning.
arXiv:2607. 13854v2 Announce Type: replace Abstract: Multimodal agents that think with images iteratively manipulate visual evidence and invoke tools across many steps.